@inproceedings{webson-etal-2020-undocumented,
    title = "Are {``}Undocumented Workers{''} the Same as {``}Illegal Aliens{''}? {D}isentangling Denotation and Connotation in Vector Spaces",
    author = "Webson, Albert  and
      Chen, Zhizhong  and
      Eickhoff, Carsten  and
      Pavlick, Ellie",
    booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)",
    month = nov,
    year = "2020",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2020.emnlp-main.335",
    doi = "10.18653/v1/2020.emnlp-main.335",
    pages = "4090--4105",
    abstract = "In politics, neologisms are frequently invented for partisan objectives. For example, {``}undocumented workers{''} and {``}illegal aliens{''} refer to the same group of people (i.e., they have the same denotation), but they carry clearly different connotations. Examples like these have traditionally posed a challenge to reference-based semantic theories and led to increasing acceptance of alternative theories (e.g., Two-Factor Semantics) among philosophers and cognitive scientists. In NLP, however, popular pretrained models encode both denotation and connotation as one entangled representation. In this study, we propose an adversarial nerual netowrk that decomposes a pretrained representation as independent denotation and connotation representations. For intrinsic interpretability, we show that words with the same denotation but different connotations (e.g., {``}immigrants{''} vs. {``}aliens{''}, {``}estate tax{''} vs. {``}death tax{''}) move closer to each other in denotation space while moving further apart in connotation space. For extrinsic application, we train an information retrieval system with our disentangled representations and show that the denotation vectors improve the viewpoint diversity of document rankings.",
}